© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17005
    Prev
    Next
    INDEX
    Explanations

    positive or negative changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auh
    -0.08
    å®īåİ¿
    -0.07
     irr
    -0.07
     непÑĢ
    -0.07
     deepest
    -0.06
     Abst
    -0.06
    åĴĮåħ¶ä»ĸ
    -0.06
    Äĩu
    -0.06
    è¿´
    -0.06
    ä¸Ŀ毫ä¸į
    -0.06
    POSITIVE LOGITS
    åıįä¹ĭ
    0.12
     Conversely
    0.09
     vice
    0.08
     favored
    0.08
    åĢ¾åIJijäºİ
    0.07
    ä¸Ĭæī¬
    0.07
     favoured
    0.07
    tml
    0.07
    UserCode
    0.07
    åħ®
    0.07
    Activations Density 0.018%

    No Known Activations